Universum Prescription: Regularization using Unlabeled Data Universum Prescription: Regularization using Unlabeled Data
Paper summary This paper apply temporal convolutional neural network on character input to learn abstract text concepts. Depending on application, the model can output the category of text or review sentiment. The model is trained from character level and do not require knowledge of syntax or semantic structure. Therefore, the model can work for various language including English and Chinese with little prior knowledge of languages.
arxiv.org
scholar.google.com
Universum Prescription: Regularization using Unlabeled Data
Zhang, Xiang and LeCun, Yann
arXiv e-Print archive - 2015 via Bibsonomy
Keywords: dblp


Loading...
Your comment:


Short Science allows researchers to publish paper summaries that are voted on and ranked!
About